OmniVoice
π
830
High-quality voice cloning TTS for 600+ languages
A versatile, all-in-one OCR model
Extract text, tables, formulas, and charts from images
Generate audio from text using voice selection
Demo for Nanonets-OCR
Nanonets / olmOCR / RolmOCR / Aya-Vision / Qwen2-VL-OCR
Stylized TTS β design voice, accent, and emotion your way
Web Localization powered by Holo1
MiMo-VL-7B-RL